Train one epoch SFT on UltraChat200K
Zizhuo Zhang PRO
resistz
AI & ML interests
None yet
Recent Activity
published a model about 12 hours ago
resistz/RLCR-Qwen3-4B-HotpotTriviaQA10K-3Epoch updated a model 7 days ago
resistz/RLCR-Calibrated-Qwen3-8B-DAPO-Math14k-3Epoch-330Step published a model 7 days ago
resistz/RLCR-Calibrated-Qwen3-8B-DAPO-Math14k-3Epoch-330StepOrganizations
models 15
resistz/RLCR-Qwen3-4B-HotpotTriviaQA10K-3Epoch
Updated
resistz/RLCR-Calibrated-Qwen3-8B-DAPO-Math14k-3Epoch-330Step
8B • Updated • 14
resistz/SFT_Qwen3-8B_DAPO17k_CorrectFormatSFT_2K
8B • Updated • 21
resistz/SFT_Llama-3.1-8B-Instruct_DAPO17k_CorrectFormatSFT_2K
8B • Updated • 15
resistz/RLCR-Calibrated-Qwen3-4B-DAPO-Math14k-3Epoch-330Step
4B • Updated • 50
resistz/GT-GRPO_Llama-3.2-3B-Instruct_NQ-HotpotQA
Updated
resistz/sft_Llama-3.2-1B_ultra200k
Text Generation • 0.3B • Updated • 3
resistz/sft_Qwen3-8B-Base_ultra200k_merged
8B • Updated • 1
resistz/sft_Qwen3-8B-Base_ultra200k_lora32
Text Generation • Updated • 2
resistz/sft_Qwen3-4B-Base_ultra200k
Text Generation • 1B • Updated • 3
datasets 0
None public yet